Surface mine slope hidden danger intelligent identification method based on unmanned aerial vehicle technology

Abstract

The invention discloses a surface mine slope hidden danger intelligent identification method based on an unmanned aerial vehicle technology, and relates to the technical field of hidden danger identification. Measuring points are set, vertical point cloud data and inclined point cloud data of the measuring points are acquired, a point cloud optimization model is constructed by combining measurement parameters, original point cloud data and measurement parameters of the mine slope are acquired, optimized point cloud data are acquired by utilizing the point cloud optimization model to construct a three-dimensional model, real-time image data of the mine slope are acquired, and a real-scene model is generated. Obtaining side slope parameters of the mine side slope, obtaining the step height of the mine side slope by combining the measurement parameters, constructing a side slope evaluation model to obtain the side slope height of the mine side slope, setting a height threshold value, obtaining an ultrahigh area by combining the side slope height, and carrying out visualization processing on the ultrahigh area; the accuracy of the three-dimensional model is improved, and whether the mine slope is ultrahigh or not can be recognized and fed back in time.

Description

Technical Field

[0001] The present invention relates to the technical field of hidden danger identification, and in particular to an intelligent identification method for hidden dangers in open-pit mine slopes based on unmanned aerial vehicle technology. Background Art

[0002] Using drones to identify hidden dangers on open-pit mine slopes is an efficient, accurate and low-cost monitoring method. This method combines drone mapping technology, image processing technology and data analysis technology. It has the advantages of strong emergency response capability, high mapping efficiency, high data accuracy, convenient operation and high safety. It plays an important role in mine slope monitoring and disaster prevention. In the prior art, when collecting point cloud data of mine slopes, the data are often collected at an angle. Therefore, the collected point cloud data will have some errors to a greater or lesser extent, resulting in a lack of accuracy in the constructed three-dimensional model. In addition, in the prior art, whether a mine slope is superelevated is often determined based on simple image recognition. This method has large deviations and cannot be accurate to the specific slope position, resulting in inaccurate recognition results. In view of the shortcomings of the prior art, the present invention provides an intelligent identification method for open-pit mine slope hazards based on drone technology. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent identification method for open-pit mine slope hazards based on unmanned aerial vehicle technology.

[0004] The purpose of the present invention can be achieved by the following technical solution: A method for intelligently identifying hidden dangers of open-pit mine slopes based on drone technology, comprising the following steps: Step S1: Set a number of measurement points on the mine slope, use a drone to obtain vertical point cloud data and inclined point cloud data of each measurement point, obtain measurement parameters of each inclined point cloud data, and build a point cloud optimization model in combination with the corresponding vertical point cloud data; Step S2: obtaining the original point cloud data and its measurement parameters of the mine slope, obtaining the optimized point cloud data using the point cloud optimization model, and constructing the corresponding three-dimensional model; Step S3: acquiring real-time image data of the mine slope, generating a real-scene model in combination with the three-dimensional model, acquiring slope parameters of the mine slope in the real-scene model, and acquiring step slope angles and step heights of the mine slope in combination with the measured parameters; Step S4: constructing a slope assessment model, and using the slope assessment model to obtain the slope height of the mine slope; Step S5: Set a height threshold for the mine slope, obtain the superelevation area based on the slope height, and visualize the superelevation area.

[0005] Furthermore, a number of measuring points are set on the mine slope, and the process of using drones to obtain vertical point cloud data and inclined point cloud data of each measuring point includes: Several measurement points are randomly set on a single mine slope and different mine slopes. Each measurement point is used as a reference to obtain the measurement normal of the plane where the measurement point is located on the mine slope. The drone is treated as a point to obtain the measurement distance between the drone and the measurement point. The angle between the line connecting the UAV and the measuring point and the measuring normal is taken as the measuring angle, the point cloud data of the measuring point obtained when the UAV is on the measuring normal is taken as the vertical point cloud data, and the point cloud data of the measuring point obtained when the UAV moves outside the measuring normal is taken as the inclined point cloud data.

[0006] Furthermore, the process of obtaining the measurement parameters of each inclined point cloud data and building a point cloud optimization model in combination with the corresponding vertical point cloud data includes: For a single measurement point, the drone is continuously moved to obtain multiple tilt point cloud data and their corresponding measurement distance and measurement angle, which are used as measurement parameters. Generate a point cloud optimization set based on the tilt point cloud data and measurement parameters of different measurement points and their corresponding vertical point cloud data, and divide it into an optimized training set and an optimized test set; Constructing a convolutional neural network, using different tilted point cloud data and measurement parameters in the optimized training set and their corresponding vertical point cloud data as input data and output data of the convolutional neural network, respectively, and training the convolutional neural network to obtain a first initial convolutional neural network; The first initial convolutional neural network is model verified using the optimized test set, and the first initial convolutional neural network with a value less than or equal to a preset first test error threshold is output as the point cloud optimization model.

[0007] Furthermore, the process of obtaining the original point cloud data and its measurement parameters of the mine slope, obtaining the optimized point cloud data using the point cloud optimization model, and constructing the corresponding three-dimensional model includes: In the actual application scenario, the original point cloud data of each point on the entire mine slope is collected by drones, and the corresponding points on the mine slope where the normal line of the drone is located when collecting the mine slope are taken as actual measurement points, and the actual measurement normal line is obtained; Obtaining measurement parameters of each point in the original point cloud data, and inputting the original point cloud data and its measurement parameters of each point into the point cloud optimization model to obtain corresponding optimized point cloud data; The point cloud features of the mine slope are extracted according to the optimized point cloud data of each point, and the optimized point cloud data are fused to obtain the optimized point cloud data set of the mine slope. The grid generation algorithm is used to convert the optimized point cloud data set into a continuous three-dimensional model.

[0008] Furthermore, the real-time image data of the mine slope is obtained, and a real-scene model is generated in combination with the three-dimensional model. The process of obtaining the slope parameters of the mine slope in the real-scene model includes: Using a drone to obtain real-time image data of the mine slope, the real-time image data includes pixel values ​​of each point on the mine slope, and mapping the pixel values ​​of each point to a corresponding position in a three-dimensional model to generate a real-scene model of the mine slope; In the real-scene model, the geometric features of the slope points are used and based on the principle of domain similarity, the slope points are divided into different regions. The regional growing method is used to perform hierarchical slope segmentation on the mine slope to obtain different steps, and the step top lines and step bottom lines of different steps are obtained. The slope parameters include the step top lines and step bottom lines of different steps on the mine slope.

[0009] Furthermore, the process of obtaining the step slope angle and step height of the mine slope in combination with the measurement parameters includes: Obtain the measurement parameters of a single point on the bottom line of the step slope, take the line corresponding to the measured distance as the measurement line, take the plane where the point is located on the mine slope as the measurement plane, and take the angle between the measurement line and the measurement plane as the measurement plane angle according to the measurement angle; The horizontal line angle between the measuring line and the horizontal line is obtained, and the step slope angle of the point is obtained according to the measuring plane angle and the horizontal line angle. The shortest distance between the point and the top line of the step slope is recorded as the slope distance. The corresponding step height is obtained according to the slope distance and the step slope angle. This method is used to obtain the step height of each point on the bottom line of the step slope and the step slope angle and step height on different steps on the mine slope.

[0010] Furthermore, a slope assessment model is constructed, and the process of obtaining the slope height of the mine slope using the slope assessment model includes: Generate a slope evaluation set based on the measured plane angle, horizontal line angle, slope distance and corresponding step height of different points on the bottom line of the step slope, and divide it into an evaluation training set and an evaluation test set; Constructing a convolutional neural network, taking the measured plane angle, horizontal line angle, slope distance and corresponding step height of different points in the evaluation training set as input data and output data of the convolutional neural network, respectively, and training the convolutional neural network to obtain a second initial convolutional neural network; The second initial convolutional neural network is model verified using the evaluation test set, and an initial convolutional neural network with a second test error threshold value that is less than or equal to a preset value is output as a slope evaluation model. The measured plane angle, horizontal line angle and slope distance of each point on the mine slope are input into the slope assessment model to obtain the corresponding slope height. The slope height refers to the minimum height difference between each point on the mine slope and the top line of the step slope.

[0011] Furthermore, a height threshold is set for the mine slope, and the super-high area is obtained in combination with the slope height. The process of visualizing the super-high area includes: Set corresponding height thresholds for different mine slopes, obtain the actual height of each point on the mine slope, the actual height is equal to the sum of the step heights of the step where each point is located and the step below, minus the slope height of each point, and compare the actual height of each point with the height threshold respectively; The points whose actual height is greater than the height threshold are regarded as superelevation points, and the area formed by all superelevation points on the mine slope is regarded as the superelevation area. In the real-scene model, the superelevation area is highlighted to achieve visualization, and a superelevation signal is generated and fed back to relevant personnel.

[0012] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention obtains the tilted point cloud data of the measuring point under different measurement parameters and constructs the corresponding point cloud optimization model, which can optimize the original point cloud data collected by the drone and then construct the corresponding three-dimensional model, which can effectively reduce the influence of different measurement parameters on the point cloud data and is conducive to improving the accuracy of the three-dimensional model; 2. The present invention generates a real-life model based on the three-dimensional model, obtains the slope parameters of the mine slope and the slope height of each point on the mine slope in the real-life model, and then obtains the actual height of each point, which is compared with a preset height threshold to obtain the super-elevation area. This can effectively reduce the deviation in height recognition through image analysis, accurately recognize the height to each point on the mine slope, and timely identify and provide feedback on whether the mine slope is super-elevated. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 is a flow chart of the present invention; Figure 2 Schematic diagram of the mine slope cross section. DETAILED DESCRIPTION

[0014] like Figure 1 As shown, an intelligent identification method for slope hazards in open-pit mines based on drone technology includes the following steps: Step S1: Set a number of measurement points on the mine slope, use a drone to obtain vertical point cloud data and inclined point cloud data of each measurement point, obtain measurement parameters of each inclined point cloud data, and build a point cloud optimization model in combination with the corresponding vertical point cloud data; Step S2: obtaining the original point cloud data and its measurement parameters of the mine slope, obtaining the optimized point cloud data using the point cloud optimization model, and constructing the corresponding three-dimensional model; Step S3: acquiring real-time image data of the mine slope, generating a real-scene model in combination with the three-dimensional model, acquiring slope parameters of the mine slope in the real-scene model, and acquiring step slope angles and step heights of the mine slope in combination with the measured parameters; Step S4: constructing a slope assessment model, and using the slope assessment model to obtain the slope height of the mine slope; Step S5: Set a height threshold for the mine slope, obtain the superelevation area based on the slope height, and visualize the superelevation area.

[0015] It should be further explained that, in the specific implementation process, several measuring points are set on the mine slope, and the process of using drones to obtain vertical point cloud data and inclined point cloud data of each measuring point includes: Several measurement points are randomly set on a single mine slope and different mine slopes. Taking each measurement point as a reference, the vertical point cloud data and the inclined point cloud data of each measurement point are obtained by using drones. Take any measurement point as an example, obtain the normal line of the plane where the measurement point is located on the mine slope, that is, the measurement normal line, treat the drone as a point for processing, and when the drone is on the measurement normal line, obtain the straight-line distance between the drone and the measurement point, that is, the measurement distance; The angle between the line between the drone and the measurement point and the measurement normal (acute angle) is taken as the measurement angle. When the drone is on the measurement normal, its measurement angle is zero, and the point cloud data of the measurement point obtained at this time is recorded as vertical point cloud data. Move the drone outside the measurement normal, record the point cloud data of the measurement point obtained at this time as inclined point cloud data, and obtain the corresponding measurement distance and measurement angle. Based on the measurement point and measurement normal, align the vertical point cloud data and the inclined point cloud data to the same coordinate system, and bind each point cloud data with its corresponding measurement distance and measurement angle.

[0016] It should be further explained that, in the specific implementation process, the process of obtaining the measurement parameters of various inclined point cloud data and building a point cloud optimization model in combination with the corresponding vertical point cloud data includes: For a single measurement point, the drone is continuously moved to obtain multiple tilted point cloud data and their corresponding measurement distance and measurement angle. The two are used as measurement parameters. The same method is used to obtain the vertical point cloud data and multiple tilted point cloud data and their corresponding measurement parameters of each measurement point. Generate a point cloud optimization set according to the tilted point cloud data and measurement parameters of different measurement points and their corresponding vertical point cloud data, and divide the obtained point cloud optimization set into an optimization training set and an optimization test set; Constructing a convolutional neural network, taking different tilted point cloud data and measurement parameters in the optimized training set as input data of the convolutional neural network, taking corresponding vertical point cloud data in the optimized training set as output data of the convolutional neural network, and training the convolutional neural network to obtain a first initial convolutional neural network; The first initial convolutional neural network is model verified using the optimized test set, and the first initial convolutional neural network with a value less than or equal to a preset first test error threshold is output as the corresponding point cloud optimization model.

[0017] It should be further explained that, in the specific implementation process, the process of obtaining the original point cloud data and its measurement parameters of the mine slope, obtaining the optimized point cloud data using the point cloud optimization model, and constructing the corresponding three-dimensional model includes: In the actual application scenario, the drone is used to collect the point cloud data of the entire mine slope, and the collected point cloud data is recorded as the original point cloud data of the mine slope. The corresponding point of the normal line where the drone is located when collecting the mine slope is taken as the actual measurement point, and the corresponding actual measurement normal line is obtained; The original point cloud data includes the point cloud data of the actual measurement point and the point cloud data of each point other than the actual measurement point, and obtains the measurement parameters corresponding to each point, including the measurement distance and the measurement angle, inputs the original point cloud data of each point and its measurement parameters into the point cloud optimization model, and outputs the corresponding optimized point cloud data through the point cloud optimization model; The number of actual measurement points is not fixed, and it is determined according to the size of the mine slope. The optimized point cloud data under different actual measurement points can be integrated into a unified coordinate system and registered using a registration algorithm. The optimized point cloud data under a single actual measurement point is taken as an example. The point cloud features of the mine slope are extracted according to the optimized point cloud data of each point. The point cloud features include corner points, edges, and surface normals. The optimized point cloud data after the above processing are fused to obtain the optimized point cloud data set of the mine slope. The grid generation algorithm is used to convert the optimized point cloud data set into a continuous grid model, that is, a three-dimensional model.

[0018] It should be further explained that, in the specific implementation process, the real-time image data of the mine slope is obtained, and the real-scene model is generated by combining the three-dimensional model. The process of obtaining the slope parameters of the mine slope in the real-scene model includes: Taking any mine slope as an example, a drone is used to obtain real-time image data of the mine slope, wherein the real-time image data includes pixel values ​​of each point on the mine slope, and a real-scene model of the mine slope is generated by mapping the pixel values ​​of each point to the corresponding position in the three-dimensional model; In the real scene model, the geometric features of the slope points (such as slope, aspect, elevation, etc.) are used for division. The slope points refer to specific locations on the terrain surface. Their geometric features are used to describe the terrain undulations and morphological changes. Based on the principle of division of domain similarity, the slope points with similar geometric features are divided into the same category and area. The mine slope is segmented into hierarchical slopes using the region growing method to obtain different steps. The region growing method is an image segmentation technology that aggregates pixel points according to the similar properties of pixels in the same region, extracts the slope contour using the concave hull algorithm, and fits the step line based on the Bezier curve to obtain the corresponding step top line and step bottom line. The slope parameters include the step top line and step bottom line of different steps on the mine slope.

[0019] It should be further explained that, in the specific implementation process, the process of obtaining the step slope angle and step height of the mine slope in combination with the measurement parameters includes: Take any point on the bottom line of the step slope as an example, obtain the measurement parameters of the point, take the line corresponding to the measured distance as the measurement line, and take the plane where the point is located on the mine slope as the measurement plane. According to the measurement angle, the angle between the measurement line and the measurement plane can be obtained, which is recorded as the measurement plane angle. Obtain the angle between the measuring line and the horizontal line, recorded as the horizontal line angle, and obtain the step slope angle of the point according to the measuring plane angle and the horizontal line angle. The step slope angle, the measuring plane angle, and the horizontal line angle are in the same plane, and the sum is 180 degrees; Get the shortest distance between the point and the top line of the step slope, record it as the slope distance, and get the corresponding step height based on the slope distance and the step slope angle. Use the same method to get the step height of each point on the bottom line of the step slope, as well as the step slope angle and step height on different steps on the mine slope.

[0020] It should be further explained that, in the specific implementation process, the process of constructing a slope assessment model and obtaining the slope height of the mine slope using the slope assessment model includes: Generate a slope evaluation set based on the measured plane angle, horizontal line angle, slope distance and corresponding step height of different points on the bottom line of the step slope, and divide the obtained slope evaluation set into an evaluation training set and an evaluation test set; Constructing a convolutional neural network, taking the measured plane angles, horizontal line angles, and slope distances at different points in the evaluation training set as input data of the convolutional neural network, taking the corresponding step heights in the evaluation training set as output data of the convolutional neural network, and training the convolutional neural network to obtain a second initial convolutional neural network; Using the evaluation test set to perform model verification on the second initial convolutional neural network, outputting an initial convolutional neural network that is less than or equal to a preset second test error threshold as the corresponding slope evaluation model; Input the measured plane angle, horizontal line angle and slope distance of any point on the mine slope into the slope assessment model to generate the corresponding slope height, which refers to the minimum height difference between any point on the mine slope and the top line of the step slope; The difference between the step height and the step height is that the step height refers to the point on the bottom line of the step slope, representing the minimum height difference between the corresponding point on the bottom line of the step slope and the top line of the step slope, while the slope height refers to any point on the mine slope, representing the minimum height difference between the corresponding point and the top line of the step slope.

[0021] It should be further explained that, in the specific implementation process, a height threshold is set for the mine slope, and the super-high area is obtained in combination with the slope height. The process of visualizing the super-high area includes: Set corresponding height thresholds for different mine slopes, obtain the actual height of each point on the mine slope, the actual height is equal to the sum of the step heights of the step where each point is located and the step below, minus the slope height of each point, compare the actual height of each point with the height threshold, if the actual height is greater than the height threshold, mark the point as a superelevation point, if the actual height is less than or equal to the height threshold, do not perform any other operations on it; The area formed by all superelevation points on the mine slope is marked as a superelevation area, and the superelevation area is highlighted in the real-life model to achieve visualization, and a corresponding superelevation signal is generated and fed back to relevant personnel.

[0022] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. An intelligent identification method for open-pit mine slope hazards based on drone technology, characterized in that: The following steps are involved: Step S1: Set a number of measurement points on the mine slope, use a drone to obtain vertical point cloud data and inclined point cloud data of each measurement point, obtain measurement parameters of each inclined point cloud data, and build a point cloud optimization model in combination with the corresponding vertical point cloud data; Step S2: obtaining the original point cloud data and its measurement parameters of the mine slope, obtaining the optimized point cloud data using the point cloud optimization model, and constructing the corresponding three-dimensional model; Step S3: acquiring real-time image data of the mine slope, generating a real-scene model in combination with the three-dimensional model, acquiring slope parameters of the mine slope in the real-scene model, and acquiring step slope angles and step heights of the mine slope in combination with the measured parameters; Step S4: constructing a slope assessment model, and using the slope assessment model to obtain the slope height of the mine slope; Step S5: Set a height threshold for the mine slope, obtain the superelevation area based on the slope height, and visualize the superelevation area.

2. According to claim 1, a method for intelligently identifying hidden dangers of open-pit mine slopes based on drone technology is characterized in that: The process of obtaining vertical point cloud data and inclined point cloud data includes: Several measurement points are randomly set on a single mine slope and different mine slopes. Each measurement point is used as a reference to obtain the measurement normal of the plane where the measurement point is located on the mine slope. The drone is treated as a point to obtain the measurement distance between the drone and the measurement point. The angle between the line connecting the UAV and the measuring point and the measuring normal is taken as the measuring angle, the point cloud data of the measuring point obtained when the UAV is on the measuring normal is taken as the vertical point cloud data, and the point cloud data of the measuring point obtained when the UAV moves outside the measuring normal is taken as the inclined point cloud data.

3. The method for intelligently identifying hidden dangers of open-pit mine slopes based on drone technology according to claim 2 is characterized in that: The process of obtaining measurement parameters and building a point cloud optimization model includes: For a single measurement point, the drone is continuously moved to obtain multiple tilt point cloud data and their corresponding measurement distance and measurement angle, which are used as measurement parameters. Generate a point cloud optimization set based on the tilt point cloud data and measurement parameters of different measurement points and their corresponding vertical point cloud data, and divide it into an optimized training set and an optimized test set; Constructing a convolutional neural network, using different tilted point cloud data and measurement parameters in the optimized training set and their corresponding vertical point cloud data as input data and output data of the convolutional neural network, respectively, and training the convolutional neural network to obtain a first initial convolutional neural network; The first initial convolutional neural network is model verified using the optimized test set, and the first initial convolutional neural network with a value less than or equal to a preset first test error threshold is output as the point cloud optimization model.

4. The method for intelligently identifying hidden dangers of open-pit mine slopes based on drone technology according to claim 3 is characterized in that: The process of obtaining optimized point cloud data and building a 3D model includes: In the actual application scenario, the original point cloud data of each point on the entire mine slope is collected by drones, and the corresponding points on the mine slope where the normal line of the drone is located when collecting the mine slope are taken as actual measurement points, and the actual measurement normal line is obtained; Obtaining measurement parameters of each point in the original point cloud data, and inputting the original point cloud data and its measurement parameters of each point into the point cloud optimization model to obtain corresponding optimized point cloud data; The point cloud features of the mine slope are extracted according to the optimized point cloud data of each point, and the optimized point cloud data are fused to obtain the optimized point cloud data set of the mine slope. The grid generation algorithm is used to convert the optimized point cloud data set into a continuous three-dimensional model.

5. The method for intelligently identifying hidden dangers of open-pit mine slopes based on drone technology according to claim 4 is characterized in that: The process of generating a real-life model and obtaining slope parameters includes: Using a drone to obtain real-time image data of the mine slope, the real-time image data includes pixel values ​​of each point on the mine slope, and mapping the pixel values ​​of each point to a corresponding position in a three-dimensional model to generate a real-scene model of the mine slope; In the real-scene model, the geometric features of the slope points are used and based on the principle of domain similarity, the slope points are divided into different regions. The regional growing method is used to perform hierarchical slope segmentation on the mine slope to obtain different steps, and the step top lines and step bottom lines of different steps are obtained. The slope parameters include the step top lines and step bottom lines of different steps on the mine slope.

6. The method for intelligently identifying hidden dangers of open-pit mine slopes based on drone technology according to claim 5 is characterized in that: The process of obtaining the step slope angle and step height includes: Obtain the measurement parameters of a single point on the bottom line of the step slope, take the line corresponding to the measured distance as the measurement line, take the plane where the point is located on the mine slope as the measurement plane, and take the angle between the measurement line and the measurement plane as the measurement plane angle according to the measurement angle; The horizontal line angle between the measuring line and the horizontal line is obtained, and the step slope angle of the point is obtained according to the measuring plane angle and the horizontal line angle. The shortest distance between the point and the top line of the step slope is recorded as the slope distance. The corresponding step height is obtained according to the slope distance and the step slope angle. This method is used to obtain the step height of each point on the bottom line of the step slope and the step slope angle and step height on different steps on the mine slope.

7. The method for intelligently identifying hidden dangers of open-pit mine slopes based on drone technology according to claim 6 is characterized in that: The process of building a slope assessment model and obtaining slope height includes: Generate a slope evaluation set based on the measured plane angle, horizontal line angle, slope distance and corresponding step height of different points on the bottom line of the step slope, and divide it into an evaluation training set and an evaluation test set; Constructing a convolutional neural network, taking the measured plane angle, horizontal line angle, slope distance and corresponding step height of different points in the evaluation training set as input data and output data of the convolutional neural network, respectively, and training the convolutional neural network to obtain a second initial convolutional neural network; The second initial convolutional neural network is model verified using the evaluation test set, and an initial convolutional neural network with a second test error threshold value that is less than or equal to a preset value is output as a slope evaluation model. The measured plane angle, horizontal line angle and slope distance of each point on the mine slope are input into the slope assessment model to obtain the corresponding slope height. The slope height refers to the minimum height difference between each point on the mine slope and the top line of the step slope.

8. The method for intelligently identifying hidden dangers of open-pit mine slopes based on drone technology according to claim 7 is characterized in that: The process of obtaining and visualizing superelevation areas includes: Set corresponding height thresholds for different mine slopes, obtain the actual height of each point on the mine slope, the actual height is equal to the sum of the step heights of the step where each point is located and the step below, minus the slope height of each point, and compare the actual height of each point with the height threshold respectively; The points whose actual height is greater than the height threshold are regarded as superelevation points, and the area formed by all superelevation points on the mine slope is regarded as the superelevation area. In the real-scene model, the superelevation area is highlighted to achieve visualization, and a superelevation signal is generated and fed back to relevant personnel.

Images